Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     africano
    -0.75
     africaine
    -0.68
     extérieure
    -0.68
     africain
    -0.66
     chimique
    -0.66
    RegressionTest
    -0.65
     virginity
    -0.65
     preuves
    -0.63
     negroes
    -0.63
    antaranya
    -0.63
    POSITIVE LOGITS
     into
    0.90
     a
    0.75
     INTO
    0.69
     Into
    0.69
    queryInterface
    0.68
     the
    0.64
    Bronnen
    0.62
     position
    0.62
    setu
    0.61
    Into
    0.61
    Act Density 0.049%

    No Known Activations